Model comparison
GPT-5.1 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 49.0 on the Noometry Index.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. GPT-5.1 scores higher in 3 categories and Qwen3.8 Max in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 52.2.
- The biggest single-benchmark swing is Mystery Game Puzzles: 19% for GPT-5.1 and 38% for Qwen3.8 Max.
- Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- Qwen3.8 Max accepts more context: 1M tokens versus 400K.
Side by side
| GPT-5.1 | Qwen3.8 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 49.0 | 56.8 |
| Released | 2025-11-13 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $10 | $6 |
| Results tracked | 63 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
GPT-5.1: 46.4 (#66), Qwen3.8 Max: 53.5 (#29)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena WebDev | 1395 | 1674 |
| SciCode | 43.3% | 53.2% |
| LMArena Coding | 1454 | 1502 |
| SWE-bench Verified | 68% | — |
| DeepSWE | — | 57.5% |
| SWE-bench Verified (bash only) | 66% | — |
| FrontierSWE | — | 17.8% |
| GSO | 13.7% | — |
| WeirdML | 60.8% | — |
| LiveBench Coding | 72.5% | — |
| ALE-Bench | 1,192 | — |
Agentic & Tool Use Qwen3.8 Max leads
GPT-5.1: 32.7 (#60), Qwen3.8 Max: 45.4 (#14)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| DeepResearch Bench | 42.8% | — |
| GDP.pdf | — | 23.2% |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning Qwen3.8 Max leads
GPT-5.1: 39.8 (#58), Qwen3.8 Max: 54.4 (#26)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| CritPt | 4.9% | 20% |
| Chess Puzzles | 32% | 40% |
| LMArena Hard Prompts | 1457 | 1496 |
| Mystery Game Puzzles | 19% | 38% |
| DTBench | 90.1% | 92% |
| LMCA | 43.9% | 46.2% |
| Epoch Capabilities Index | 149.64 | 156.41 |
| ARC-AGI-2 | 17.6% | — |
| SimpleBench | 53.2% | — |
| NYT Connections (extended) | — | 88.3% |
| ARC-AGI-1 | 72.8% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math Qwen3.8 Max leads
GPT-5.1: 52.2 (#51), Qwen3.8 Max: 73.2 (#20)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 100% |
| LMArena Math | 1447 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge Qwen3.8 Max leads
GPT-5.1: 50.6 (#71), Qwen3.8 Max: 61.7 (#27)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 87.6% | 92.7% |
| SimpleQA Verified | 48% | 47.3% |
| LMArena Expert | 1470 | 1507 |
| Humanity's Last Exam | 23.7% | — |
| MMLU-Pro | 57.9% | — |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), Qwen3.8 Max: 37.2 (#75)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1250 | 1314 |
| VPCT | 58.7% | — |
| Furniture Assembly | — | 20% |
| LMArena Document | 1403 | — |
Multilingual Qwen3.8 Max leads
GPT-5.1: 53.8 (#56), Qwen3.8 Max: 56.7 (#18)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1431 | 1472 |
| LMArena Chinese | 1495 | 1538 |
| LMArena French | 1450 | 1503 |
| LMArena German | 1438 | 1483 |
| LMArena Japanese | 1453 | 1467 |
| LMArena Korean | 1401 | 1461 |
| LMArena Russian | 1435 | 1481 |
| LMArena Spanish | 1433 | 1492 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Qwen3.8 Max: 77.6 (#17)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1443 | 1479 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Qwen3.8 Max: 45.6 (#31)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1447 | 1489 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference Qwen3.8 Max leads
GPT-5.1: 64.5 (#55), Qwen3.8 Max: 67.1 (#30)
| Benchmark | GPT-5.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1443 | 1483 |
| LMArena Creative Writing | 1427 | 1479 |
| LMArena Multi-Turn | 1450 | 1489 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 49.0 on the Noometry Index.
Which is cheaper, GPT-5.1 or Qwen3.8 Max?
Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 46.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 400K.
How many benchmarks do GPT-5.1 and Qwen3.8 Max share?
29 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Qwen3.8 Max has 39.